What are the hardware requirements for ASMv2?

ASMv2 requires approximately 26.6 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed ASMv2 and how large is it?

ASMv2 is developed by OpenGVLab, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate ASMv2?

ASMv2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

ASMv2 by OpenGVLab — VRAM 26.6GB, 4K context

Name: ASMv2
Author: OpenGVLab

ASMv2 is an open-source language model by OpenGVLab. Features: 13b LLM, VRAM: 26.6GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.13.

Endpoints compatible Llava Pytorch Region:us Sharded

Model Card on HF 🤗: https://huggingface.co/OpenGVLab/ASMv2

ASMv2 Benchmarks

LLME Score: 0.12611

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

ASMv2 Parameters and Internals

Model Type

chatbot, multimodal, text generation, scene graph generation

Use Cases

Areas:

research on large multimodal models and chatbots

Training Details

Data Sources:

CC12M, AS-1B, GRiT

Methodology:

fine-tuning LLaMA/Vicuna on multimodal instruction-following data

LLM Name	ASMv2
Repository 🤗	https://huggingface.co/OpenGVLab/ASMv2
Model Size	13b
Required VRAM	26.6 GB
Updated	2026-05-18
Maintainer	OpenGVLab
Model Type	llava
Model Files	9.9 GB: 1-of-3 9.9 GB: 2-of-3 6.8 GB: 3-of-3
Model Architecture	LlavaLlamaForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.31.0
Tokenizer Class	LlamaTokenizer
Beginning of Sentence Token	<s>
End of Sentence Token	</s>
Unk Token	<unk>
Vocabulary Size	32000
Torch Data Type	bfloat16

Best Alternatives to ASMv2

Best Alternatives	Context / RAM	Downloads	Likes
Llava V1.5 13B	4K / 26 GB	16200	527
Llava V1.6 Vicuna 13B	4K / 26.7 GB	3001	61
Evalalign V1.0 13B	4K / 26.7 GB	6	1
Table Llava V1.5 13B	4K / 26.6 GB	13	1
Peenoblanc 52 Llava	4K / 26.7 GB	6	0
Otterchecker	4K / 26.7 GB	1	2
Llava 13B Custom	4K / 26.7 GB	5	0
V Mllm 13B	4K / 26.6 GB	4	1
...roduct Taxonomy Llava V1.6 13B	4K / 26.7 GB	7	0
Som Llava V1.5 13B	4K / 26.7 GB	12	5

Note: green Score (e.g. "73.2") means that the model is better than OpenGVLab/ASMv2.

Rank the ASMv2 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 53972 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

ASMv2 by OpenGVLab

» All LLMs » OpenGVLab » ASMv2 URL Share it on

ASMv2 Benchmarks

ASMv2 Parameters and Internals

Best Alternatives to ASMv2

Rank the ASMv2 Capabilities

What open-source LLMs or SLMs are you in search of? 53972 in total.